Benjamin Milde

Improving Unsupervised Sparsespeech Acoustic Models with Categorical\n Reparameterization

2020 · arXiv (Cornell University)

The Sparsespeech model is an unsupervised acoustic model that can generate\ndiscrete pseudo-labels for untranscribed speech. We extend the Sparsespeech\nmodel to allow for sampling over a random discrete variable, yielding\npseudo-posteriorgrams. The degree of sparsity in this …